{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T10:42:20Z","timestamp":1785840140600,"version":"3.56.0"},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,10,1]]},"DOI":"10.1109\/iros55552.2023.10341629","type":"proceedings-article","created":{"date-parts":[[2023,12,13]],"date-time":"2023-12-13T14:17:55Z","timestamp":1702477075000},"page":"5606-5613","source":"Crossref","is-referenced-by-count":16,"title":["Nonprehensile Planar Manipulation through Reinforcement Learning with Multimodal Categorical Exploration"],"prefix":"10.1109","author":[{"given":"Juan","family":"Del Aguila Ferrandis","sequence":"first","affiliation":[{"name":"School of Informatics, The University of Edinburgh,Edinburgh,UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jo\u00e3o","family":"Moura","sequence":"additional","affiliation":[{"name":"School of Informatics, The University of Edinburgh,Edinburgh,UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sethu","family":"Vijayakumar","sequence":"additional","affiliation":[{"name":"School of Informatics, The University of Edinburgh,Edinburgh,UK"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1177\/027836498600500303"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1177\/02783649922067762"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1177\/0278364920913938"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/lra.2017.2720845"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/icra.2017.7989345"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/robot.1989.100081"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/icra46639.2022.9811942"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/icra.2018.8460528"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/simpar.2018.8376268"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.3389\/fnbot.2022.829437"},{"key":"ref11","author":"Jeong","year":"2019","journal-title":"Modelling generalized forces with reinforcement learning for sim-to-real transfer"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/icra48891.2023.10161496"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/icra.2016.7487155"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abk2822"},{"key":"ref15","author":"Schulman","year":"2017","journal-title":"Proximal policy optimization algorithms"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919887447"},{"key":"ref17","author":"Heess","year":"2017","journal-title":"Emergence of locomotion behaviours in rich environments"},{"key":"ref18","article-title":"High-dimensional continuous control using generalized advantage estimation","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"Schulman","year":"2016"},{"key":"ref19","author":"Mnih","year":"2013","journal-title":"Playing atari with deep reinforcement learning"},{"key":"ref20","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proceedings of the 35th International Conference on Machine Learning","volume":"80","author":"Haarnoja","year":"2018"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6059"},{"key":"ref22","first-page":"2016","volume-title":"Pybuliet, a python module for physics simulation for games, robotics and machine learning","author":"Coumans"},{"issue":"268","key":"ref23","first-page":"1","article-title":"Stable-baselines3: Reliable reinforcement learning implementations","volume":"22","author":"Raffin","year":"2021","journal-title":"Journal of Machine Learning Research"},{"key":"ref24","author":"Kingma","year":"2014","journal-title":"Adam: A method for stochastic optimization"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/icra48891.2023.10161272"},{"key":"ref26","first-page":"1411","article-title":"Ros-pybullet interface: A framework for reliable contact simulation and human-robot interaction","volume-title":"Proceedings of The 6th Conference on Robot Learning","author":"Mower","year":"2023"},{"key":"ref27","first-page":"158","article-title":"Implicit behavioral cloning","volume-title":"Proceedings of the 5th Conference on Robot Learning","author":"Florence","year":"2022"}],"event":{"name":"2023 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Detroit, MI, USA","start":{"date-parts":[[2023,10,1]]},"end":{"date-parts":[[2023,10,5]]}},"container-title":["2023 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10341341\/10341342\/10341629.pdf?arnumber=10341629","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,19]],"date-time":"2023-12-19T19:23:26Z","timestamp":1703013806000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10341629\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,1]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/iros55552.2023.10341629","relation":{},"subject":[],"published":{"date-parts":[[2023,10,1]]}}}